Amazon Polly · Capability
Amazon Polly Text-to-Speech
Workflow capability for converting text to lifelike speech using Amazon Polly. Combines speech synthesis, voice discovery, and lexicon management for developers building voice-enabled applications.
What You Can Do
POST
Synthesize speech
— Convert text to speech audio
/v1/speech
GET
List voices
— List available voices by language and engine
/v1/voices
GET
List lexicons
— List pronunciation lexicons
/v1/lexicons
PUT
Create lexicon
— Create or update a pronunciation lexicon
/v1/lexicons
POST
Start task
— Start an asynchronous speech synthesis task
/v1/tasks
GET
List tasks
— List synthesis tasks
/v1/tasks
MCP Tools
synthesize-speech
Convert text to lifelike speech audio using Amazon Polly
list-voices
List available Amazon Polly voices filterable by language and engine type
read-only
list-lexicons
List custom pronunciation lexicons for controlling how words are spoken
read-only
get-lexicon
Get the content of a pronunciation lexicon
read-only
create-lexicon
Create or update a custom pronunciation lexicon
start-synthesis-task
Start an asynchronous synthesis task for long text with S3 output
list-synthesis-tasks
List and monitor asynchronous speech synthesis tasks
read-only
APIs Used
amazon-polly